Passenger travel route inferencing in a subway system

Abstract

A computer-implemented method is presented for inferring passenger routes in a subway system. The method includes identifying, via an imaging device, a target passenger within the subway system, employing an exiting flow extractor to determine passenger exiting waves, employing an exiting wave identifier to mark an exiting wave of the passenger exiting waves including the target passenger, employing a supporting evidence backtracer to determine an entrance gate for each of the passengers in the marked exiting wave including the target passenger, determining a route probability for each of the passengers in the marked exiting wave including the target passenger via voting or distribution estimation processing, and employing a most probable route inferer to infer a route of the target passenger based on an aggregate route probability for all the passengers in the marked exiting wave.

Description

BACKGROUNDTechnical Field[0001]The present invention relates generally to mass transit systems, and more specifically, to passenger travel route inferencing in a subway system.Description of the Related Art[0002]Often, management and control of mass transit systems cannot keep up with the growth in passenger traffic. Traffic peaks occur daily during work commutes, during bad weather, or during sporting and other events drawing large crowds. Traffic peaks can lead to bottlenecks and potential breakdowns in the system. Frequently, passengers only board a subway car or train at a few locations, for example, in the vicinity of access points such as escalators or stairs, leaving some doors of the subway train unused. Passengers are likely to avoid traveling any distance to another door because it is unknown whether the car further down has available seats. Thus, the majority of passengers prefer to board at the door closest to them, rather than using a door further away and taking the ri...

AI Technical Summary

Benefits of technology

The patent describes a method, system, and computer-readable storage medium for inferring the routes of passengers in a subway system using an imaging device and an exiting flow extractor to determine the wave of passenger arrivals. The system also uses an exiting wave identifier to mark the wave of the target passenger, a supporting evidence backtracer to determine the entrance gate for each passenger, and a most probable route inferer to infer the route of the passenger based on the route probability for all the passengers in the marked wave. The technical effects of this patent include improved passenger safety and efficiency in subway systems through advanced route prediction and monitoring.

Problems solved by technology

Often, management and control of mass transit systems cannot keep up with the growth in passenger traffic.

Traffic peaks can lead to bottlenecks and potential breakdowns in the system.

Frequently, passengers only board a subway car or train at a few locations, for example, in the vicinity of access points such as escalators or stairs, leaving some doors of the subway train unused.

This can alter the flow distribution on different routes and cause further passenger traffic.

Images